© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58311
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouis
    -0.07
    æ³Ĭ
    -0.07
    reté
    -0.07
    å¼ĢæĿ¥
    -0.06
    vert
    -0.06
     keynote
    -0.06
    halen
    -0.06
    æĥļ
    -0.06
    querque
    -0.06
    æī¶çĿĢ
    -0.06
    POSITIVE LOGITS
    CDATA
    0.07
    artin
    0.07
    æĹ¢åı¯
    0.07
    ansfer
    0.07
    _stamp
    0.07
    astes
    0.07
    ç¿°
    0.06
    agogue
    0.06
    ipt
    0.06
    sWith
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.